Merge branch 'worktree-agent-a76ce40c73601d90d' into overnight-jul31

internal/router/llmrouter_test.go

@@ -175,3 +175,87 @@ func TestLLMRouterLLMError(t *testing.T) {
 		t.Fatal("want ok=false, err!=nil on llm error")
 	}
 }
+
+// --- slot extraction on top of an LLM decision --------------------------------
+
+// newLLMTestRouter — a router whose route always comes from the mock model.
+func newLLMTestRouter(t *testing.T, out string) *Router {
+	t.Helper()
+	c := NewClassifier(NewHashEmbedder(1024))
+	seedClassifier(t, c)
+	acts := DefaultActMatcher{Fns: []string{"restart", "stop", "run", "backup"}}
+	return New(Config{
+		Classifier: c,
+		Extractor:  Extractor{Time: StubDateTimeParser{}, Acts: acts, Facts: DefaultFactParser{}},
+		Threshold:  0.4,
+		LLM:        NewLLMRouter(mockLLM{out: out}),
+	})
+}
+
+// The model cannot produce a fire time, so without extraction every LLM-routed
+// reminder was dropped as "no time".
+func TestLLMDecisionGetsReminderTime(t *testing.T) {
+	r := newLLMTestRouter(t, `{"intent":"reminder","text":"позвонить маме"}`)
+	d, err := r.Route(context.Background(), "напомни позвонить маме через 2 часа", refNow())
+	if err != nil {
+		t.Fatalf("route: %v", err)
+	}
+	if d.Intent != IntentReminder {
+		t.Fatalf("want reminder, got %v", d.Intent)
+	}
+	if !d.Slots.HasTime || !d.Slots.Time.Equal(refNow().Add(2*time.Hour)) {
+		t.Fatalf("want time now+2h, got %+v", d.Slots)
+	}
+	if d.Slots.Text != "позвонить маме" {
+		t.Fatalf("extraction overwrote the model's text: %q", d.Slots.Text)
+	}
+}
+
+// No time in the utterance ⇒ no time in the slots. Do not invent one; the
+// daemon says it could not read the time.
+func TestLLMReminderWithoutTimeStaysEmpty(t *testing.T) {
+	r := newLLMTestRouter(t, `{"intent":"reminder","text":"позвонить маме"}`)
+	d, err := r.Route(context.Background(), "напомни позвонить маме", refNow())
+	if err != nil {
+		t.Fatalf("route: %v", err)
+	}
+	if d.Slots.HasTime {
+		t.Fatalf("invented a time: %v", d.Slots.Time)
+	}
+}
+
+// An act decision arrived with no Fn, so the tool never ran.
+func TestLLMDecisionGetsActFn(t *testing.T) {
+	r := newLLMTestRouter(t, `{"intent":"act","verb":"restart nginx"}`)
+	d, err := r.Route(context.Background(), "слушай, restart nginx пожалуйста", refNow())
+	if err != nil {
+		t.Fatalf("route: %v", err)
+	}
+	if !d.Slots.HasFn || d.Slots.Fn != "restart" || len(d.Slots.Args) != 1 || d.Slots.Args[0] != "nginx" {
+		t.Fatalf("want fn=restart args=[nginx], got %+v", d.Slots)
+	}
+}
+
+// The model's own slots win; extraction only fills gaps.
+func TestLLMSlotsWinOverExtraction(t *testing.T) {
+	r := newLLMTestRouter(t, `{"intent":"fact","key":"hydration","value":"выпил"}`)
+	d, err := r.Route(context.Background(), "я выпил воду", refNow())
+	if err != nil {
+		t.Fatalf("route: %v", err)
+	}
+	if d.Slots.Key != "hydration" {
+		t.Fatalf("extraction overwrote the model's key: %q", d.Slots.Key)
+	}
+}
+
+// A fact the model left keyless still gets one from the parser.
+func TestLLMFactGetsKeyFromParser(t *testing.T) {
+	r := newLLMTestRouter(t, `{"intent":"fact","text":"я выпил воду"}`)
+	d, err := r.Route(context.Background(), "я выпил воду", refNow())
+	if err != nil {
+		t.Fatalf("route: %v", err)
+	}
+	if !d.Slots.HasKey || d.Slots.Key != "water" {
+		t.Fatalf("want key=water, got %+v", d.Slots)
+	}
+}

internal/router/router.go

@@ -88,6 +88,7 @@ func (r *Router) Route(ctx context.Context, utterance string, now time.Time) (De
 	if r.llm != nil {
 		if d, ok, err := r.llm.Route(ctx, utterance, now); err == nil && ok {
 			d.Utterance = utterance
+			r.fillSlots(ctx, &d, now)
 			return d, nil
 		} else if err != nil {
 			log.Printf("router: llm route fell back to classifier: %v", err)
@@ -118,6 +119,39 @@ func (r *Router) Route(ctx context.Context, utterance string, now time.Time) (De
 	return d, nil
 }
 
+// fillSlots — run stage-2 extraction on an LLM decision and fill only the slots
+// the model left empty. The LLM wins where it answered: it saw the sentence, the
+// parsers are keyword tables. Extraction covers what the model cannot produce at
+// all — a parsed reminder time and an allowlist fn.
+//
+// If a reminder still has no time, leave it missing. The daemon then says it
+// could not read the time; inventing one would set a wrong alarm.
+func (r *Router) fillSlots(ctx context.Context, d *Decision, now time.Time) {
+	ex := r.extractor.Extract(ctx, d.Intent, d.Utterance, now)
+	if !d.Slots.HasTime && ex.HasTime {
+		d.Slots.Time, d.Slots.HasTime = ex.Time, ex.HasTime
+	}
+	if !d.Slots.HasKey && ex.HasKey {
+		d.Slots.Key, d.Slots.Value, d.Slots.HasKey = ex.Key, ex.Value, ex.HasKey
+	}
+	if !d.Slots.HasFn && ex.HasFn {
+		d.Slots.Fn, d.Slots.Args, d.Slots.HasFn = ex.Fn, ex.Args, ex.HasFn
+	}
+	// For an act the model returns the verb in Text ("restart nginx"), which is
+	// often cleaner than the raw utterance ("maven, could you restart nginx").
+	// Try it too when the utterance did not match the allowlist.
+	if d.Intent == IntentAct && !d.Slots.HasFn && r.extractor.Acts != nil &&
+		d.Slots.Text != "" && d.Slots.Text != d.Utterance {
+		if fn, args, ok := r.extractor.Acts.Match(d.Slots.Text); ok {
+			d.Slots.Fn, d.Slots.Args, d.Slots.HasFn = fn, args, true
+		}
+	}
+	if d.Slots.Text == "" {
+		d.Slots.Text = ex.Text
+	}
+	// Stage stays 1: it says who decided the route, and that was the LLM.
+}
+
 // CorrectMisroute — the user corrected a bad classification. Appends a new
 // example for the corrected intent (append-only — grows the classifier, no
 // retrain). Same shape as nudges.outcome tuning cooldowns: more reliable over